{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WP4JXUDEHFFDE5O3GQ5Q7C7TNS","short_pith_number":"pith:WP4JXUDE","schema_version":"1.0","canonical_sha256":"b3f89bd064394a3275db343b0f8bf36ca95e40acc35df6609ee081198d913a98","source":{"kind":"arxiv","id":"1711.11566","version":1},"attestation_state":"computed","paper":{"title":"Hybrid VAE: Improving Deep Generative Models using Partial Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew Fitzgibbon, Sebastian Nowozin, Sergey Tulyakov","submitted_at":"2017-11-30T18:37:37Z","abstract_excerpt":"Deep neural network models trained on large labeled datasets are the state-of-the-art in a large variety of computer vision tasks. In many applications, however, labeled data is expensive to obtain or requires a time consuming manual annotation process. In contrast, unlabeled data is often abundant and available in large quantities. We present a principled framework to capitalize on unlabeled data by training deep generative models on both labeled and unlabeled data. We show that such a combination is beneficial because the unlabeled data acts as a data-driven form of regularization, allowing "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1711.11566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-30T18:37:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d771c43ded899ca1dd78911965cc1169209a08e6f5292625381c339f698da421","abstract_canon_sha256":"3e4a45906a78d4069b5ee0afce401440190bc7f8e1e44fa4e3eedfafb9d8dd43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:11.261702Z","signature_b64":"eX7C9W8iJjsZrpeiFTXzdN06uBbznU9F1+8rhec/yBvv0rCafX+XyeQKGVgqg7wASelRUE2BgsPyNGGhFkyCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3f89bd064394a3275db343b0f8bf36ca95e40acc35df6609ee081198d913a98","last_reissued_at":"2026-05-18T00:29:11.261083Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:11.261083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid VAE: Improving Deep Generative Models using Partial Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrew Fitzgibbon, Sebastian Nowozin, Sergey Tulyakov","submitted_at":"2017-11-30T18:37:37Z","abstract_excerpt":"Deep neural network models trained on large labeled datasets are the state-of-the-art in a large variety of computer vision tasks. In many applications, however, labeled data is expensive to obtain or requires a time consuming manual annotation process. In contrast, unlabeled data is often abundant and available in large quantities. We present a principled framework to capitalize on unlabeled data by training deep generative models on both labeled and unlabeled data. We show that such a combination is beneficial because the unlabeled data acts as a data-driven form of regularization, allowing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11566","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.11566","created_at":"2026-05-18T00:29:11.261169+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.11566v1","created_at":"2026-05-18T00:29:11.261169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11566","created_at":"2026-05-18T00:29:11.261169+00:00"},{"alias_kind":"pith_short_12","alias_value":"WP4JXUDEHFFD","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WP4JXUDEHFFDE5O3","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WP4JXUDE","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS","json":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS.json","graph_json":"https://pith.science/api/pith-number/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/graph.json","events_json":"https://pith.science/api/pith-number/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/events.json","paper":"https://pith.science/paper/WP4JXUDE"},"agent_actions":{"view_html":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS","download_json":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS.json","view_paper":"https://pith.science/paper/WP4JXUDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.11566&json=true","fetch_graph":"https://pith.science/api/pith-number/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/graph.json","fetch_events":"https://pith.science/api/pith-number/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/action/storage_attestation","attest_author":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/action/author_attestation","sign_citation":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/action/citation_signature","submit_replication":"https://pith.science/pith/WP4JXUDEHFFDE5O3GQ5Q7C7TNS/action/replication_record"}},"created_at":"2026-05-18T00:29:11.261169+00:00","updated_at":"2026-05-18T00:29:11.261169+00:00"}